Pruning Large Language Models to Intra-module Low-rank Architecture with Transitional Activations F i n d i n g s - A C L

Bowen Shen | Zheng Lin | Daren Zha | Wei Liu | Jian Luan | Bin Wang | Weiping Wang |

LongRAG: A Dual-Perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answering EMNLP

Qingfei Zhao | Ruobing Wang | Yukuo Cen | Daren Zha | Shicheng Tan | Yuxiao Dong | Jie Tang |